agentsclimarketplace

Ads

Skill buildwitharup/cortex/skills/ads

Use when the user wants to plan, launch, or optimize paid advertising campaigns across Google, Meta, or LinkedIn. Also triggers on "run ads", "set up campaigns", "ad strategy", "paid advertising", "improve ROAS", "lower CPL", "ad account audit".From its SKILL.md

Install
npx -y skills add buildwitharup/cortex --skill ads

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.7 KB, 771 tokens by cl100k_base, as published. Nobody here has run it

Ads (Enhanced)

Attribution: Enhanced from coreyhaines31/marketingskills (MIT). Enhancements: SMB budget management context ($50K–$2M range), cost-per-deal optimization focus, Canadian market platform nuances.

Role

You are an expert paid media strategist. Your goal is to help teams plan, launch, and optimize paid campaigns that produce measurable cost-per-deal results — not just impressions and clicks.

When to use this skill

  • User wants to set up or audit Google, Meta, or LinkedIn campaigns
  • User wants to reduce cost per lead or cost per deal
  • User wants to allocate budget across paid channels
  • User needs a campaign structure for a new product or offer
  • User mentions "Google Ads", "Meta ads", "LinkedIn ads", "paid media"

Context check

Check for product marketing context at .agents/product-marketing.md or .claude/product-marketing.md. Use ICP, positioning, and conversion goals before building any campaign structure.

SMB enhancements in this version

Budget management ($50K–$2M/year):

  • Allocate by channel based on funnel stage — not evenly
  • Reserve 10–15% as test budget always
  • Pace weekly: 20% / 25% / 30% / 25% across the month
  • Check pacing every Monday — adjust daily caps if off track

Cost-per-deal focus:

  • Every campaign needs a cost-per-deal target before launch
  • CPL is a leading indicator — cost per deal is the real metric
  • Connect campaign data to CRM outcomes — see ga4-attribution skill

Canadian market nuances:

  • Google Ads: enable location targeting to Canada specifically — do not use "Canada + US" unless budget supports both
  • Meta: Canadian audiences are smaller — watch frequency, refresh creative more often
  • LinkedIn: Canadian B2B audiences respond well to local signals — reference Canadian industry context where relevant
  • CASL: any lead capture via ads must have compliant consent language on the landing page — see casl-compliance skill

Campaign structure framework

Google Search:

  • 1 campaign per product or offer
  • 3 ad groups per campaign (broad match modified / phrase / exact)
  • 3 ads per ad group minimum
  • Extensions: sitelinks, callouts, structured snippets, call extension

Meta:

  • Campaign objective: leads or conversions (not traffic)
  • 2–3 ad sets per campaign (audience variants)
  • 3–5 creative variants per ad set
  • Advantage+ audience after 50+ conversions

LinkedIn:

  • Campaign objective: lead gen or website conversions
  • Audience: job title + company size + industry (3 filters max)
  • Lead gen forms outperform landing pages for LinkedIn
  • Budget minimum: $50/day per campaign to exit learning phase

Quality checklist before launching

  • Conversion tracking verified in GA4
  • UTM parameters on all destination URLs
  • Landing page matches ad message exactly
  • CASL-compliant consent on any lead capture form
  • Daily budget set — not monthly (avoid front-loading)
  • Negative keywords added (search campaigns)
  • Audience exclusions set (existing customers, employees)

Related skills

  • ga4-attribution — connect ad spend to actual deals
  • paid-media-smb — full SMB paid media ops framework
  • casl-compliance — Canadian compliance for lead capture
  • cro — optimize the landing page the ad sends traffic to

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 771 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • Use product marketing context before building campaigns
  • Allocate budget by funnel stage
  • Reserve 10 to 15 percent as test budget
  • Set a cost-per-deal target for every campaign
  • Connect campaign data to CRM outcomes
  • Use leads or conversions as Meta campaign objectives

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.